Started implementing bert in server

ADA/SA/bert_analyzer.py

@@ -12,7 +12,7 @@ import shap
 
 semeval_2014_train_path = 'data/SemEval-2014/Laptop_Train_v2.xml'
 semeval_2014_test_path = 'data/SemEval-2014/Laptops_Test_Gold.xml'
-amazon_test_path = 'data/Amazon/amazon_camera_test.xml'
+amazon_test_path = 'data/Amazon/annotated_amazon_laptop_reviews.xml'
 trained_model_path = 'semeval_2014_2.pt'
 
 BATCH_SIZE = 32
@@ -26,6 +26,12 @@ def loss(outputs, labels):
 
 class BertAnalyzer:
 
+    @staticmethod
+    def default():
+        sa = BertAnalyzer()
+        sa.load_saved('semeval_2014.pt')
+        return sa
+
     def load_saved(self, path):
         self.net = TDBertNet(len(polarity_indices))
         self.net.load_state_dict(torch.load(path))
@@ -93,7 +99,7 @@ class BertAnalyzer:
         f1 = metrics.f1_score(truths, predicted, labels=range(len(polarity_indices)), average='macro')
         print('macro F1:', f1)
 
-    def analyze_sentence(self, text, char_from, char_to):
+    def get_sentiment_polarity(self, text, char_from, char_to):
         instance = Instance(text, char_from, char_to)
         tokens, tg_from, tg_to = instance.get()
         text, target_indices = instance.to_tensor()
@@ -116,10 +122,18 @@ class BertAnalyzer:
         #     ax.set_xticklabels(tokens, rotation=45, rotation_mode='anchor', ha='right')
         # plt.show()
 
-        _, pred = torch.max(outputs.data, 1)
-        return pred
-
-
-sentiment_analyzer = BertAnalyzer()
-sentiment_analyzer.load_saved('semeval_2014.pt')
-print(sentiment_analyzer.analyze_sentence("Well built laptop with win7.", 11, 17))
\ No newline at end of file
+        val, pred = torch.max(outputs.data, 1)
+        if pred == 0:
+            # positive
+            return val
+        elif pred == 1:
+            # negative
+            return -val
+        else:
+            # neutral or conflicted
+            return 0
+
+
+sentiment_analyzer = BertAnalyzer.default()
+sentiment_analyzer.evaluate(semeval_2014_test_path)
+sentiment_analyzer.evaluate(amazon_test_path)

ADA/SA/sentiment_analyzer.py

@@ -11,6 +11,7 @@ from sklearn.feature_extraction.text import CountVectorizer
 import os
 import math
 
+
 def resample_data(instances, labels):
     label_instances = {label: [instance for instance in instances if instance.opinion == label] for label in labels}
     max_n_instances = max([len(v) for v in label_instances.values()])
@@ -22,6 +23,7 @@ def resample_data(instances, labels):
     print(len(resampled_data))
     return resampled_data
 
+
 class SentimentAnalyzer:
 
     expr_clf = svm.SVC() # determines if sentence expresses sentiment towards ARG
@@ -39,10 +41,11 @@ class SentimentAnalyzer:
     def expresses_sentiment(self, instances):
         return self.expr_clf.predict([instance.vector for instance in instances])
 
+
 semeval_2014_train_path = 'data/SemEval-2014/SemEval_2014_Laptop_Train_with_labelled_parse_trees.xml'
 semeval_2014_test_path = 'data/SemEval-2014/SemEval_2014_Laptop_Test_with_labelled_parse_trees.xml'
 amazon_train_path = 'data/Amazon/amazon_camera_train.xml'
-amazon_test_path = 'data/Amazon/amazon_camera_test2.xml' # 'data/Amazon/prepared_amazon_camera_reviews.xml'
+amazon_test_path = 'data/Amazon/amazon_camera_test2.xml'  # 'data/Amazon/prepared_amazon_camera_reviews.xml'
 semeval_train_path = 'data/SemEval-2016/ABSA16_Laptops_Train_SB1_v2_with_labelled_parse_trees.xml'
 semeval_test_path = 'data/SemEval-2016/ABSA16_Laptops_Test_with_labelled_parse_trees.xml' #
 tweet_train_path = 'data/acl-14-short-data/tweet_train_with_labelled_parse_trees.xml'
@@ -56,7 +59,7 @@ sa = SentimentAnalyzer()
 
 train_tree = ET.parse(train_path)
 train_instances = [Instance(instance) for instance in train_tree.getroot()]
-train_instances = resample_data(train_instances, labels)
+# train_instances = resample_data(train_instances, labels)
 
 # create and train vectorizer model
 vec = Vectorizer(train_instances)

ADA/SA/vectorizer.py

@@ -17,7 +17,7 @@ class Vectorizer:
         self.transformer = TfidfTransformer()
 
         # indep features:
-        self.bow_vectorizer = CountVectorizer(stop_words='english', ngram_range=(1,2))
+        self.bow_vectorizer = CountVectorizer(stop_words='english', ngram_range=(1,5))
         texts = [instance.text for instance in train_instances]
         train_bow_vectors = self.bow_vectorizer.fit_transform(texts).toarray()
         train_sent_vectors = [self.sentiment_scores(instance) for instance in train_instances]

ADA/agent.py

@@ -5,11 +5,12 @@ from anytree import PostOrderIter
 import pickle
 from argument import *
 from functools import reduce
-
+from SA.bert_analyzer import BertAnalyzer
 
 class Agent:
     sentiment_threshold = 0.95
     review_tokenizer = ReviewTokenizer()
+    bert_analyzer = BertAnalyzer.default()
 
     def __init__(self):
         # load classifier
@@ -27,7 +28,7 @@ class Agent:
         return phrases
 
     # analyze sentiment
-    def get_sentiment(self, phrase):
+    def get_bayes_sentiment(self, phrase):
         # get classification
         tokens = self.review_tokenizer.tokenize_review(phrase)
         prob_classification = self.classifier.prob_classify(dict([token, True] for token in tokens))
@@ -35,6 +36,9 @@ class Agent:
         strength = (prob_classification.prob(classification) - 0.5) * 2
         return strength if classification == '+' else -strength
 
+    def get_bert_sentiment(self, text, char_from, char_to):
+        return self.bert_analyzer.get_sentiment_polarity(text, char_from, char_to)
+
     # remove all ancestors of node in list l
     def remove_ancestors(self, node, l):
         if node.parent != None:
@@ -51,8 +55,9 @@ class Agent:
         while len(arguments) > 0:
             f = arguments.pop(0)
             for word in glossary[f]:
-                if word in phrase:
-                    argument_matches.append(f)
+                matches = [(f, m.start(), m.end()) for m in re.finditer(word, phrase)]
+                if matches:
+                    argument_matches += matches
                     self.remove_ancestors(f, arguments)
                     break
         return argument_matches
@@ -61,17 +66,16 @@ class Agent:
         votes = {}
         vote_phrases = {}
         for phrase in phrases:
-            arguments = self.get_arguments(phrase)
-            sentiment = self.get_sentiment(phrase)
-            if abs(sentiment) > self.sentiment_threshold:
-                for argument in arguments:
+            for argument, start, end in self.get_arguments(phrase):
+                sentiment = self.get_bayes_sentiment(phrase) # self.get_bert_sentiment(phrase, start, end)
+                if abs(sentiment) > self.sentiment_threshold:
                     if (argument not in votes) or (abs(votes[argument]) < abs(sentiment)):
                         votes[argument] = sentiment  # what if there's two phrases with same argument?
                         vote_phrases[argument] = {'phrase': phrase, 'sentiment': sentiment}
         # normalize votes to 1 (+) or -1 (-)
         for argument in votes:
             votes[argument] = 1 if votes[argument] > 0 else -1
-        return (votes, vote_phrases)
+        return votes, vote_phrases
 
     # augment votes (Definition 4.3) obtained for a single critic
     def augment_votes(self, votes):

ADA/DataLoader.py → ADA/dataloader.py

 import pandas as pd
 
-class DataLoader:
 
+class DataLoader:
     data_location = 'camera_prepared_data.tsv'
     reviews = pd.read_csv(data_location, sep='\t', error_bad_lines=False)
 

ADA/server/ios_server/views.py

@@ -4,7 +4,7 @@ import jsonpickle
 from django.views.decorators.csrf import csrf_exempt
 
 import sys
-sys.path.append('/Users/joeloksanen/individual_project/ADA')
+sys.path.append('/home/joel/individual_project/ADA')
 from dataloader import DataLoader
 from communicator import Communicator
 

ADA/server/server/settings.py

@@ -25,7 +25,7 @@ SECRET_KEY = 'z)tj_b=**v@b5-l6s!$*+_0=nzmor8dc#y$-%4%45kt8e8q@-f'
 # SECURITY WARNING: don't run with debug turned on in production!
 DEBUG = True
 
-ALLOWED_HOSTS = ['192.168.0.13', '146.169.222.109', '146.169.218.37']
+ALLOWED_HOSTS = ['192.168.1.104']
 
 
 # Application definition